qingy2024
/

PR2.1-14B-Instruct-GRPO-ckpt

Model card Files Files and versions Community

PR2.1 14B Instruct (Step 290 Checkpoint)

Training in progress...

PR2 Training Progress Bar

Progress: 290 out of 1000 steps

Downloads last month: 13

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for qingy2024/PR2.1-14B-Instruct-GRPO-ckpt

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-14B-Instruct

Finetuned

qingy2024/PR2-14B-Instruct

Adapter

(1)

this model